I don't know if the performance of Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.2 has improved or regressed because https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard/ is stuck.
Lun Zima
Lunzima
AI & ML interests
Merge & fine-tune models for personal use
Recent Activity
new activity
about 1 month ago
Lunzima/NQLSG-Qwen2.5-14B-OriginalFusion:Improve language tag
updated
a model
about 2 months ago
Lunzima/NQLSG-Qwen2-VL-2B-v2
updated
a model
about 2 months ago
Lunzima/NQLSG-Qwen2.5-14B-MegaFusion-v9.4-Coder
Organizations
None yet
Lunzima's activity
replied to
their
post
3 months ago
posted
an
update
3 months ago
Post
1340
I'm currently experimenting with the SFT dataset
Lunzima/alpaca_like_dataset to further boost the performance of NQLSG-Qwen2.5-14B-MegaFusion-v9.x. This includes data sourced from DeepSeek-R1 or other cleaned results (excluding CoTs). Additionally, datasets that could potentially enhance the model's performance in math and programming/code, as well as those dedicated to specific uses like Swahili, are part of the mix.
@sometimesanotion @sthenno @wanlige
@sometimesanotion @sthenno @wanlige
-
- 1 reply